Modern Deep Learning in Python
4.6 (1,583 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
19,965 students enrolled

Modern Deep Learning in Python

Build with modern libraries like Tensorflow, Theano, Keras, PyTorch, CNTK, MXNet. Train faster with GPU on AWS.
Bestseller
4.6 (1,583 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
19,965 students enrolled
Last updated 10/2018
English
English [Auto-generated], Indonesian [Auto-generated], 6 more
  • Italian [Auto-generated]
  • Polish [Auto-generated]
  • Portuguese [Auto-generated]
  • Romanian [Auto-generated]
  • Spanish [Auto-generated]
  • Thai [Auto-generated]
Current price: $10.00 Original price: $179.99 Discount: 94% off
30-Day Money-Back Guarantee
This course includes
  • 9 hours on-demand video
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to Udemy's top 3,000+ courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • Apply momentum to backpropagation to train neural networks
  • Apply adaptive learning rate procedures like AdaGrad, RMSprop, and Adam to backpropagation to train neural networks

  • Understand the basic building blocks of Theano

  • Build a neural network in Theano
  • Understand the basic building blocks of TensorFlow
  • Build a neural network in TensorFlow
  • Build a neural network that performs well on the MNIST dataset
  • Understand the difference between full gradient descent, batch gradient descent, and stochastic gradient descent
  • Understand and implement dropout regularization in Theano and TensorFlow
  • Understand and implement batch normalization in Theano and Tensorflow
  • Write a neural network using Keras
  • Write a neural network using PyTorch
  • Write a neural network using CNTK
  • Write a neural network using MXNet
Requirements
  • Be comfortable with Python, Numpy, and Matplotlib. Install Theano and TensorFlow.
  • If you do not yet know about gradient descent, backprop, and softmax, take my earlier course, deep learning in Python, and then return to this course.
Description

This course continues where my first course, Deep Learning in Python, left off. You already know how to build an artificial neural network in Python, and you have a plug-and-play script that you can use for TensorFlow. Neural networks are one of the staples of machine learning, and they are always a top contender in Kaggle contests. If you want to improve your skills with neural networks and deep learning, this is the course for you.

You already learned about backpropagation, but there were a lot of unanswered questions. How can you modify it to improve training speed? In this course you will learn about batch and stochastic gradient descent, two commonly used techniques that allow you to train on just a small sample of the data at each iteration, greatly speeding up training time.

You will also learn about momentum, which can be helpful for carrying you through local minima and prevent you from having to be too conservative with your learning rate. You will also learn about adaptive learning rate techniques like AdaGradRMSprop, and Adam which can also help speed up your training.

Because you already know about the fundamentals of neural networks, we are going to talk about more modern techniques, like dropout regularization and batch normalization, which we will implement in both TensorFlow and Theano. The course is constantly being updated and more advanced regularization techniques are coming in the near future.

In my last course, I just wanted to give you a little sneak peak at TensorFlow. In this course we are going to start from the basics so you understand exactly what's going on - what are TensorFlow variables and expressions and how can you use these building blocks to create a neural network? We are also going to look at a library that's been around much longer and is very popular for deep learning - Theano. With this library we will also examine the basic building blocks - variables, expressions, and functions - so that you can build neural networks in Theano with confidence.

Theano was the predecessor to all modern deep learning libraries today. Today, we have almost TOO MANY options. Keras, PyTorch, CNTK (Microsoft), MXNet (Amazon / Apache), etc. In this course, we cover all of these! Pick and choose the one you love best.

Because one of the main advantages of TensorFlow and Theano is the ability to use the GPU to speed up training, I will show you how to set up a GPU-instance on AWS and compare the speed of CPU vs GPU for training a deep neural network.

With all this extra speed, we are going to look at a real dataset - the famous MNIST dataset (images of handwritten digits) and compare against various benchmarks. This is THE dataset researchers look at first when they want to ask the question, "does this thing work?"

These images are important part of deep learning history and are still used for testing today. Every deep learning expert should know them well.

This course focuses on "how to build and understand", not just "how to use". Anyone can learn to use an API in 15 minutes after reading some documentation. It's not about "remembering facts", it's about "seeing for yourself" via experimentation. It will teach you how to visualize what's happening in the model internally. If you want more than just a superficial look at machine learning models, this course is for you.



HARD PREREQUISITES / KNOWLEDGE YOU ARE ASSUMED TO HAVE:

  • calculus

  • linear algebra

  • probability

  • Python coding: if/else, loops, lists, dicts, sets

  • Numpy coding: matrix and vector operations, loading a CSV file

  • neural networks and backpropagation


TIPS (for getting through the course):

  • Watch it at 2x.

  • Take handwritten notes. This will drastically increase your ability to retain the information.

  • Write down the equations. If you don't, I guarantee it will just look like gibberish.

  • Ask lots of questions on the discussion board. The more the better!

  • Realize that most exercises will take you days or weeks to complete.

  • Write code yourself, don't just sit there and look at my code.


WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:

  • Check out the lecture "What order should I take your courses in?" (available in the Appendix of any of my courses, including the free Numpy course)


Who this course is for:
  • Students and professionals who want to deepen their machine learning knowledge
  • Data scientists who want to learn more about deep learning
  • Data scientists who already know about backpropagation and gradient descent and want to improve it with stochastic batch training, momentum, and adaptive learning rate procedures like RMSprop
  • Those who do not yet know about backpropagation or softmax should take my earlier course, deep learning in Python, first
Course content
Expand all 77 lectures 09:04:39
+ Introduction and Outline
2 lectures 11:53

In the previous course you learned about softmax and backpropagation. What will you learn in this course?

Preview 08:05
Where does this course fit into your deep learning studies?
03:48
+ Review
2 lectures 18:44
Review of Basic Concepts
14:13

Where to get the MNIST dataset, where to put it to run the code from this course correctly. I run through util.py, which contains functions we'll be using throughout the course. I run a logistic regression benchmark to show the accuracy we should aim to beat with deep learning.

Where to get the MNIST dataset and Establishing a Linear Benchmark
04:31
+ Gradient Descent: Full vs Batch vs Stochastic
2 lectures 08:23
What are full, batch, and stochastic gradient descent?
02:45
Full vs Batch vs Stochastic Gradient Descent in code
05:38
+ Momentum and adaptive learning rates
7 lectures 52:12

How can you use momentum to speed up neural network training and get out of local minima?

Using Momentum to Speed Up Training
06:10
Nesterov Momentum
06:36
Momentum in Code
06:35

Learn about periodic decay of learning rate, exponential decay, 1/t decay, AdaGrad, and RMSprop.

Variable and adaptive learning rates
11:45
Constant learning rate vs. RMSProp in Code
04:05
Adam Optimization
11:18
Adam in Code
05:43
+ Choosing Hyperparameters
5 lectures 18:47
Hyperparameter Optimization: Cross-validation, Grid Search, and Random Search
03:19
Sampling Logarithmically
03:10
Grid Search in Code
07:11
Modifying Grid Search
01:22
Random Search in Code
03:45
+ Weight Initialization
5 lectures 19:53
Weight Initialization Section Introduction
00:58
Vanishing and Exploding Gradients
06:06
Weight Initialization
08:20
Local vs. Global Minima
02:51
Weight Initialization Section Summary
01:38
+ Theano
3 lectures 27:07
Theano Basics: Variables, Functions, Expressions, Optimization
07:47
Building a neural network in Theano
09:17
Is Theano Dead?
10:03
+ TensorFlow
3 lectures 31:18
TensorFlow Basics: Variables, Functions, Expressions, Optimization
07:27
Building a neural network in TensorFlow
09:43
What is a Session? (And more)
14:08
+ GPU Speedup, Homework, and Other Misc Topics
5 lectures 23:11

I show you how to start a GPU instance on Amazon Web Services (AWS) and prove to you that training a neural network using Theano on the GPU can be much faster than the CPU.

Setting up a GPU Instance on Amazon Web Services
07:06
Can Big Data be used to Speed Up Backpropagation?
03:21

Here are some things you can do to make yourself more confident with Theano and TensorFlow coding. They are exercises that extend the material taught in this class. I also mention a handful of topics you can look forward to hearing about in future courses.

Exercises and Concepts Still to be Covered
02:13
How to Improve your Theano and Tensorflow Skills
04:39
Theano vs. TensorFlow
05:52
+ Transition to the 2nd Half of the Course
1 lecture 05:24
Transition to the 2nd Half of the Course
05:24